DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
Acknowledgement is made of Applicant’s claim of priority from 63626229, filed January 29, 2024.
Information Disclosure Statement
The information disclosure statement (“IDS”) filed on January 28, 2025 was reviewed and the listed references were noted.
Claim Objections
Claims 3 and 6 objected to because of the following informalities: In claim 3, “venous statis risk factors” should read “venous stasis risk factors”. In claim 6, “(DVR)” should read “(DVT)”. Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite a system, method, and non-transitory computer-readable medium for risk assessment of deep vein thrombosis and pulmonary embolism using retinal images. Consider method claim 1:
Step 1:
With regard to Step 1, the instant claim is directed to a method or a process; and therefore, the claim is directed to one of the statutory categories of invention.
Step 2A, Prong One:
With regard to 2A, Prong One, the limitations “determining, by the processor, a feature in the image”, “determining, by the processor and by inputting the feature and at least a portion of the patient data as input to a machine learning (ML) model, a risk level associated with a first condition”, “determining, by the processor and based on the risk level being higher than a threshold, a recommendation for screening of the patient for the first condition” as drafted, recite an abstract idea, such as a process that, under its broadest reasonable interpretation, covers performance of the limitations manually and in the mind of a person. That is, a user or person skilled in the art may determine a feature in an image, determine from the image feature and medical records of a patient whether the patient is at risk of a disease, and determine a recommendation for the patient to be screened for the disease if the risk is higher than a certain threshold. This is the concept that falls under the grouping of abstract ideas mental processes, i.e., a concept performed in the human mind, evaluation, judgement, and/or opinion of the user.
Step 2A, Prong Two:
The 2019 PEG defines the phrase “integration into a practical application” to require an additional step or a combination of additional steps in the claim to apply, rely on, or use the judicial exception. In the instant case, the additional step of “receiving, by a processor, an image of a retina of an eye of a patient”, “receiving, by the processor and from an electronic medical record (EMR) of the patient, patient data corresponding to the patient” and “providing, by the processor and to an output device, an output indicating the recommendation” is considered to be extra-solution activity of gathering and outputting information. In addition, with respect to the system and computer-readable medium claims of claims 10-15 and 16-20, the mere recitation of a generic processor, memory, or storage medium to perform/store programming instructions of the recited/identified abstract idea does not integrate the identified abstract idea into a practical application. Accordingly, the above-mentioned additional elements/limitations do not integrate the abstract idea into a practical application; and therefore, the independent claims recite an abstract idea.
Step 2B:
Because the claims fail under Step 2A, the claims are further evaluated under Step 2B. The claims herein do not include additional elements that are sufficient to amount to significantly more than the judicial exception, because as discussed above with respect to integration of the abstract idea into practical application, the additional elements/limitations to perform the recited steps, amount to no more than insignificant extra-solution activity. Mere instructions to apply an exception using a generic component cannot provide an inventive concept. Therefore, independent claims 1, 10 and 16 are not patent eligible. In addition, claims 2-9, 11-15 and 17-20 of the instant application provide limitations that both individually or in combination do not integrate the identified abstract idea into a practical application or provide significantly more than the identified abstract idea.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 3-4, 7, 10-11, 13, 16 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Vaghefi Rezaei et al. (US 2025/0308701 A1, with foreign priority to AU2022/901625, filed June 15, 2022, US PGPub used herein for mapping purposes) in view of Kanagasingam et al. (US 9,898,659 B2).
Regarding claim 1, Vaghefi Rezaei teaches a method, comprising:
receiving, by a processor (Vaghefi Rezaei, Para. [0056], the processing system may have processing facilities represented by one or more processors), an image of a retina of an eye of a patient (Vaghefi Rezaei, Para. [0058], fundus images obtained from one or more fundus imaging devices (herein referred to as a “fundus camera”) may be input to the processing system);
determining, by the processor, a feature in the image (Vaghefi Rezaei, Para. [0075], good quality images with related labels pass through a plurality of AI models. These AI models include sets of risk contributing factor (RCF) CNNs that are trained to detect indicators of: glycaemic control, blood pressure, cholesterol, and exposure to smoking. These indicators include, but are not limited to: drusen appearance, clustering, and/or location; pigmentation change in density and/or location; arteriovenous crossing; change in arteriovenous crossing calibre and/or thickness change; arteriovenous tortuosity; retinal oedema size and/or pattern; and/or microaneurysms concentration);
determining, by the processor and by inputting the feature and at least a portion of the patient data as input to a machine learning (ML) model, a risk level associated with a first condition (Vaghefi Rezaei, Para. [0082], After the processing pipelines of fundus images and meta-information (i.e., portion of the patient data) are completed, the individual-level fundus image feature vector and meta-information vector are concatenated together to form an individual feature vector. Para. [0083], The individual feature vector is processed by a CVD risk prediction neural network model utilising a fully connected neural network (FCNN). The last layer utilizes a sigmoid function to compress the output to be between [0,1] which serves as the predicted risk/probability (i.e., risk level));
determining, by the processor and based on the risk level being higher than a threshold, a recommendation for screening of the patient for the first condition (Vaghefi Rezaei, Para. [0115], For instances in which the CVD risk is above a threshold (in this example 15%), a referral recommendation is included in the report—for example recommending a consultation with a cardiologist); and
providing, by the processor and to an output device, an output indicating the recommendation (Vaghefi Rezaei, Fig. 4D; Para. [0115], For instances in which the CVD risk is above a threshold (in this example 15%), a referral recommendation is included in the report—for example recommending a consultation with a cardiologist).
Although Vaghefi Rezaei teaches reporting on contributing factors to overall CVD risk based on patient meta-information such as age, gender, and/or ethnicity (Vaghefi Rezaei, Para. [0038]), Vaghefi Rezaei does not explicitly teach “receiving, by the processor and from an electronic medical record (EMR) of the patient, patient data corresponding to the patient”. However, in an analogous field of endeavor, Kanagasingam teaches the processing system utilises the subject identity to retrieve subject data, for example, by accessing a medical records database (i.e., electronic medical record) containing a medical record for the subject (i.e., patient) (Kanagasingam, Col. 14, lines 54-67).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date to modify the method of Vaghefi Rezaei with the teachings of Kanagasingam by including receiving patient data from an electronic medical record of the patient. One having ordinary skill in the art would have been motivated to combine these references because doing so would allow for delivering highly specialized health services, as recognized by Kanagasingam. Thus, the claimed invention would have been obvious to one having ordinary skill in the art before the effective filing date.
Regarding claim 3, Vaghefi Rezaei in view of Kanagasingam teaches the method of claim 1, wherein the portion of the patient data is indicative of at least one of: venous statis risk factors, endothelial damage risk factors, or hypercoagulability risk factors (Vaghefi Rezaei, Para. [0081], meta-information of an individual associated with the one or more fundus images is received. The meta-information includes gender, ethnicity, HbA1c, TCHDL, etc. Some of the meta-information is categorical data such as gender, ethnicity, deprivation value, medicine, etc., and other is numerical data such as age, HbA1c, etc.).
Regarding claim 4, Vaghefi Rezaei in view of Kanagasingam teaches the method of claim 3, wherein:
the venous statis risk factors comprise one or more of: sedentary lifestyle, hypertension, kidney failure, obesity, heart disease, or varicose veins (Vaghefi Rezaei, Para. [0090], non-modifiable factors (e.g. age, race, gender) and modifiable factors (e.g. glycaemic control, blood pressure, cholesterol, and exposure to smoking));
the endothelial damage risk factors comprise one or more of: non-obstructive cardiovascular disease, hyperglycemia, hypertension, or hyperlipidemia (Vaghefi Rezaei, Para. [0081], meta-information of an individual associated with the one or more fundus images is received. The meta-information includes gender, ethnicity, HbA1c, TCHDL, etc.); and
the hypercoagulability risk factors comprise one or more of: genetic factor, obesity, cancer diagnosis, medication, pregnancy, autoimmune disorder, smoking, infection, surgery, or immobilization (Vaghefi Rezaei, Para. [0090], non-modifiable factors (e.g. age, race, gender) and modifiable factors (e.g. glycaemic control, blood pressure, cholesterol, and exposure to smoking)).
Regarding claim 7, Vaghefi Rezaei in view of Kanagasingam teaches the method of claim 1, further comprising:
receiving, by the processor, follow-up information indicating whether the patient was diagnosed with the first condition (Vaghefi Rezaei, Para. [0084], the training data includes labels for each individual as to whether they encounter a CVD event (e.g., heart failure) after the fundus images been taken and meta-information has been recorded);
augmenting, by the processor, a training dataset to include a data point comprising the follow-up information, the image, and at least the portion of the patient data (Vaghefi Rezaei, Para. Para. [0084], the training data includes labels for each individual as to whether they encounter a CVD event (i.e., follow-up information) (e.g., heart failure) after the fundus images been taken and meta-information has been recorded. Para. [0086], In training, a process converts a patient information file (i.e., patient data) into a matrix. The matrix is then converted into a streamed dataset that allows for memory-efficient and time-efficient loading of images. The streamed dataset is then augmented for training purposes. The augmented streamed dataset is then optimized using the gradient descent method via optimizer and loss functions that are provided. Para. [0089], the patient's meta-data is transformed with corresponding fundus images (i.e., the image) into a streamed fashion. In an example, a data generator is created using TensorFlow which produces a mini-batch of data every time. Within each mini-batch, there are several patients visits including the biometrics and fundus images. Then the streamed dataset is fed into the model for training); and
updating, by the processor, the ML model by re-training with the augmented training dataset (Vaghefi Rezaei, Para. [0084], after having the loss term, the back-propagation method is used to calculate the gradients of each trainable parameter (218,113 parameters in an exemplary model) in terms of the final loss. Then the parameters are updated at the negative gradients direction using Adam algorithm).
Claims 10 recites a system with elements corresponding to the steps recited in Claim 1. Therefore, the recited elements of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Vaghefi Rezaei and Kanagasingam references, presented in rejection of Claim 1, apply to this claim. Finally, the combination of the Vaghefi Rezaei and Kanagasingam references discloses memory, a processor, and computer-executable instructions stored in the memory and executable by the processor (Vaghefi Rezaei, Para. [0056], the processing system 1002 may have processing facilities represented by one or more processors 1004, memory 1006, and other components typically present in such computing environments. In the exemplary embodiment illustrated the memory 1006 stores information accessible by processor 1004, the information comprising instructions 1008 that may be executed by the processor).
Regarding claim 11, Vaghefi Rezaei in view of Kanagasingam teaches the system of claim 10, wherein the ML model is trained, based on a training dataset, to identify, based on the image and the patient data as inputs, the risk level associated with the first condition (Vaghefi Rezaei, Para. [0075], good quality images with related labels pass through a plurality of AI models. These AI models include sets of risk contributing factor (RCF) CNNs 2010, to 2010, that are trained to detect indicators of: glycaemic control, blood pressure, cholesterol, and exposure to smoking. These indicators include, but are not limited to: drusen appearance, clustering, and/or location; pigmentation change in density and/or location; arteriovenous crossing; change in arteriovenous crossing calibre and/or thickness change; arteriovenous tortuosity; retinal oedema size and/or pattern; and/or microaneurysms concentration Para. [0082], After the processing pipelines of fundus images and meta-information (i.e., patient data) are completed, the individual-level fundus image feature vector and meta-information vector are concatenated together to form an individual feature vector. Para. [0083], The individual feature vector is processed by a CVD risk prediction neural network model utilising a fully connected neural network (FCNN). The last layer utilizes a sigmoid function to compress the output to be between [0,1] which serves as the predicted risk/probability (i.e., risk level)).
Regarding claim 13, Vaghefi Rezaei in view of Kanagasingam teaches the system of claim 10, further comprising:
receiving, by the processor, follow-up information indicating whether the patient was diagnosed with the first condition (Vaghefi Rezaei, Para. [0084], the training data includes labels for each individual as to whether they encounter a CVD event (e.g., heart failure) after the fundus images been taken and meta-information has been recorded);
augmenting, by the processor, a training dataset to include a data point comprising the follow-up information, and the feature, and at least the portion of the patient data (Vaghefi Rezaei, Para. Para. [0084], the training data includes labels for each individual as to whether they encounter a CVD event (i.e., follow-up information) (e.g., heart failure) after the fundus images been taken and meta-information has been recorded. Para. [0086], In training, a process converts a patient information file (i.e., patient data) into a matrix. The matrix is then converted into a streamed dataset that allows for memory-efficient and time-efficient loading of images. The streamed dataset is then augmented for training purposes. The augmented streamed dataset is then optimized using the gradient descent method via optimizer and loss functions that are provided. Para. [0089], the patient's meta-data is transformed with corresponding fundus images (i.e., the feature) into a streamed fashion. In an example, a data generator is created using TensorFlow which produces a mini-batch of data every time. Within each mini-batch, there are several patients visits including the biometrics and fundus images. Then the streamed dataset is fed into the model for training); and
updating, by the processor, the ML model by re-training with the augmented training dataset (Vaghefi Rezaei, Para. [0084], after having the loss term, the back-propagation method is used to calculate the gradients of each trainable parameter (218,113 parameters in an exemplary model) in terms of the final loss. Then the parameters are updated at the negative gradients direction using Adam algorithm).
Claim 16 recites a computer-readable storage medium storing a program with instructions corresponding to the steps recited in Claim 1. Therefore, the recited programming instructions of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Vaghefi Rezaei and Kanagasingam references, presented in rejection of Claim 1, apply to this claim. Finally, the combination of Vaghefi Rezaei and Kanagasingam references discloses a computer readable storage medium (Vaghefi Rezaei, Para. [0012], a non-transitory computer-readable medium having computer-readable program code stored thereon).
Regarding claim 18, Vaghefi Rezaei in view of Kanagasingam teaches the non-transitory computer-readable storage medium of claim 16, wherein the ML model is based at least in part on determining, in a training dataset, a correlation between the first condition and the feature or the EMR data (Vaghefi Rezaei, Para. [0084], the training data includes labels for each individual as to whether they encounter a CVD event (e.g., heart failure) after the fundus images been taken and meta-information has been recorded).
Claims 2 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Vaghefi Rezaei et al. (US 2025/0308701 A1, with foreign priority to AU2022/901625, filed June 15, 2022, US PGPub used herein for mapping purposes) in view of Kanagasingam et al. (US 9,898,659 B2), as applied to claims 1, 3-4, 7, 10-11, 13, 16 and 18 above, and further in view of Bressler et al. (US 8,896,682 B2).
Regarding claim 2, Vaghefi Rezaei in view of Kanagasingam teaches the method of claim 1, as described above.
Although Vaghefi Rezaei in view of Kanagasingam teaches detecting features in fundus images (Vaghefi Rezaei, Para. [0075]), the references do not explicitly teach “wherein the feature comprises at least one of: a cotton wool spot (CWS), Roth spots, a retinal vein occlusion (RVO), a retinal hemorrhage, or an emboli in a retinal blood vessel”. However, in an analogous field of endeavor, Bressler teaches abnormalities (i.e., features) that may be detected may include diabetic retinopathy, retinal vein occlusions, a vitreomacular interface abnormality, a macular hole, an epiretinal membrane, optic nerve pathologies, glaucomatous optic nerve damage, and/or other pathologies (Bressler, Col. 14, lines 24-30).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the method of Vaghefi Rezaei in view of Kanagasingam with the teachings of Bressler by including the detected feature is a retinal vein occlusion. One having ordinary skill in the art would have been motivated to combine these references because doing so would allow for detecting abnormalities of the eye, as recognized by Bressler. Thus, the claimed invention would have been obvious to one having ordinary skill in the art before the effective filing date.
Regarding claim 19, Vaghefi Rezaei in view of Kanagasingam teaches the non-transitory computer-readable storage medium of claim 16, wherein:
the EMR data comprises at least one of: a blood pressure measurement of the patient, a length of hospital stay or surgical procedures performed during the hospital stay (Vaghefi Rezaei, Para. [0075], these AI models include sets of risk contributing factor (RCF) CNNs that are trained to detect indicators of: glycaemic control, blood pressure, cholesterol, and exposure to smoking).
Although Vaghefi Rezaei in view of Kanagasingam teaches detecting features in fundus images (Vaghefi Rezaei, Para. [0075]), the references do not explicitly teach “the feature comprises at least one of: an emboli in a blood vessel of the retina, cotton wool spots (CWS), Roth spots, or a retinal vein occlusion (RVO)”. However, in an analogous field of endeavor, Bressler teaches abnormalities (i.e., features) that may be detected may include diabetic retinopathy, retinal vein occlusions, a vitreomacular interface abnormality, a macular hole, an epiretinal membrane, optic nerve pathologies, glaucomatous optic nerve damage, and/or other pathologies (Bressler, Col. 14, lines 24-30).
The proposed combination as well as the motivation for combining the Vaghefi Rezaei, Kanagasingam and Bressler references presented in the rejection of Claim 2, apply to Claim 19 and are incorporated herein by reference. Thus, the computer readable medium recited in Claim 19 is met by Vaghefi Rezaei in view of Kanagasingam further in view of Bressler.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Vaghefi Rezaei et al. (US 2025/0308701 A1, with foreign priority to AU2022/901625, filed June 15, 2022, US PGPub used herein for mapping purposes) in view of Kanagasingam et al. (US 9,898,659 B2), as applied to claims 1, 3-4, 7, 10-11, 13, 16 and 18 above, and further in view of Baronov et al. (US 2013/0054264 A1).
Regarding claim 5, Vaghefi Rezaei in view of Kanagasingam teaches the method of claim 1, as described above.
Although Vaghefi in view of Kanagasingam teaches recommending a patient be screened for a disease (Vaghefi Rezaei, Para. [0115]), the references do not explicitly teach “wherein the recommendation is based at least in part on a length of stay in a hospital bed”. However, in an analogous field of endeavor, Baronov teaches types of risks that are considered for determining the recommended treatment include, but are not limited to, morbidity risks, mortality risks, the risks of transitioning into an adverse patient state, the risks associated with transitioning into an improved patient state, and the risks of significantly altering one or more of the physiological variables, risks associated with prolonged hospital stay (i.e., length of stay in a hospital bed), or any other risks associated with increased treatment costs to the patient, and the like (Baronov, Para. [0033]).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date to modify the method of Vaghefi Rezaei in view of Kanagasingam with the teachings of Baronov by including that the recommendation is based at least in part on length of stay in a hospital bed (i.e., prolonged hospital stay). One having ordinary skill in the art would have been motivated to combine these references because doing so would allow for reducing patient risks, as recognized by Baronov. Thus, the claimed invention would have been obvious to one having ordinary skill in the art before the effective filing date.
Claims 6, 14 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Vaghefi Rezaei et al. (US 2025/0308701 A1, with foreign priority to AU2022/901625, filed June 15, 2022, US PGPub used herein for mapping purposes) in view of Kanagasingam et al. (US 9,898,659 B2), as applied to claims 1, 3-4, 7, 10-11, 13, 16 and 18 above, and further in view of Shi et al. (US 2022/0383489 A1).
Regarding claim 6, Vaghefi Rezaei in view of Kanagasingam teaches the method of claim 1, as described above.
Although Vaghefi Rezaei in view of Kanagasingam teaches a CVD risk detection network (Vaghefi Rezaei, Para. [0083]), the references do not explicitly teach “wherein the first condition comprises deep vein thrombosis (DVR) or pulmonary embolism (PE)”. However, in an analogous field of endeavor, Shi teaches that once trained, the CAD system can be used to provide a patient-level probability for a condition, such as pulmonary embolism (Shi, Para. [0069]).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date to modify the method of Vaghefi Rezaei in view of Kanagasingam with the teachings of Shi by including that the first condition is pulmonary embolism. One having ordinary skill in the art would have been motivated to combine these references because doing so would allow for automating diagnosis of a condition such as pulmonary embolism, as recognized by Shi. Thus, the claimed invention would have been obvious to one having ordinary skill in the art before the effective filing date.
Regarding claim 14, Vaghefi Rezaei in view of Kanagasingam teaches the system of claim 10, as described above.
Although Vaghefi Rezaei in view of Kanagasingam teaches utilizing a fully connected neural network (Vaghefi Rezaei, Para. [0082]), they do not explicitly teach “wherein the ML model is based on a transformer architecture”. However, in an analogous field of endeavor, Shi teaches an attention based neural-network architecture known as a Transformer (Shi, Para. [0047]).
The proposed combination as well as the motivation for combining the Vaghefi Rezaei, Kanagasingam and Shi references presented in the rejection of Claim 6, apply to Claim 14 and are incorporated herein by reference. Thus, the system recited in Claim 14 is met by Vaghefi Rezaei in view of Kanagasingam further in view of Shi.
Claim 20 recites a computer-readable storage medium storing a program with instructions corresponding to the steps recited in Claim 6. Therefore, the recited programming instructions of this claim are mapped to the proposed combination in the same manner as the corresponding steps in its corresponding method claim. Additionally, the rationale and motivation to combine the Vaghefi Rezaei, Kanagasingam and Shi references, presented in rejection of Claim 6, apply to this claim. Finally, the combination of the Vaghefi Rezaei, Kanagasingam and Shi references discloses a computer readable storage medium (Vaghefi Rezaei, Para. [0012], a non-transitory computer-readable medium having computer-readable program code stored thereon).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Vaghefi Rezaei et al. (US 2025/0308701 A1, with foreign priority to AU2022/901625, filed June 15, 2022, US PGPub used herein for mapping purposes) in view of Kanagasingam et al. (US 9,898,659 B2), as applied to claims 1, 3-4, 7, 10-11, 13, 16 and 18 above, and further in view of Li et al. (US 2022/0165418 A1).
Regarding claim 8, Vaghefi Rezaei in view of Kanagasingam teaches the method of claim 7, wherein the training dataset includes anonymized patient data that:
include corresponding images of the retina of respective patients (Vaghefi Rezaei, Para. [0059], a fundus camera typically comprises an image capturing device, which in use is held close to the exterior of the eye and which illuminates and photographs the retina to provide a 2D image of part of the interior of the eye),
are extracted from an EMR system (Kanagasingam, Col. 14, lines 54-67, the processing system utilises the subject identity to retrieve subject data, for example, by accessing a medical records database (i.e., electronic medical record) containing a medical record for the subject), and
include an indication of whether the respective patient was diagnosed with the first condition (Vaghefi Rezaei, Para. [0084], the training data includes labels for each individual as to whether they encounter a CVD event (e.g., heart failure) after the fundus images been taken and meta-information has been recorded).
The proposed combination as well as the motivation for combining the Vaghefi Rezaei and Kanagasingam references presented in the rejection of Claim 1, apply to Claim 8 and are incorporated herein by reference.
Although Vaghefi Rezaei in view of Kanagasingam teaches training data including fundus images and labels for each individual as to whether they encounter a CVD event (Vaghefi Rezaei, Para. [0084]), the references do not explicitly teach “the training dataset includes anonymized patient data that: are associated with a plurality of hospitalized patients” However, in an analogous field of endeavor, Li teaches a diagnostic or imaging device used at the point of care such as at a hospital or outside of the clinic setting (e.g. using a portable diagnostic or imaging device at home) can be used to obtain an image of a subject that is then uploaded over a network such as the Internet for remote diagnosis using the application (Li, Para. [0085]).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date to modify the method of Vaghefi Rezaei in view of Kanagasingam with the teachings of Li by including that the patient date is associated with hospitalized patients (i.e., was taken at a point of care such as at a hospital). One having ordinary skill in the art would have been motivated to combine these references because doing so would allow for automated image-based detection of diseases, as recognized by Li. Thus, the claimed invention would have been obvious to one having ordinary skill in the art before the effective filing date.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Vaghefi Rezaei et al. (US 2025/0308701 A1, with foreign priority to AU2022/901625, filed June 15, 2022, US PGPub used herein for mapping purposes) in view of Kanagasingam et al. (US 9,898,659 B2), as applied to claims 1, 3-4, 7, 10-11, 13, 16 and 18 above, and further in view of Bai et al. (US 2025/0279187 A1, with priority to PCT/EP2023/060717, filed April 25, 2023, US PGPub used herein for mapping purposes).
Regarding claim 9, Vaghefi Rezaei in view of Kanagasingam teaches the method of claim 1, wherein the ML model is a first ML model (Vaghefi Rezaei, Para. [0075], good quality images with related labels pass through a plurality of AI models).
Although Vaghefi Rezaei in view of Kanagasingam teaches passing images through a plurality of AI models (Vaghefi Rezaei, Para. [0075]), the references do not explicitly teach “determining the feature further comprises: inputting, by the processor, the image to a second ML model” and “receiving, by the processor, and as output of the second ML model, an indication of the feature and a confidence level associated with the indication”. However, in an analogous field of endeavor, Bai teaches a confidence score (e.g. probability score) output by the model to indicate the probability that the output of the model is correct (Bai, Para. [0075]). In this embodiment, the target tissue (i.e., feature) is detecting using a ML model (Bai, Para. [0091]).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date to modify the method of Vaghefi Rezaei in view of Kanagasingam with the teachings of Bai by including inputting the image to a second ML model and receiving as output an indication of the feature (i.e., target tissue) and a confidence level (i.e., confidence score). One having ordinary skill in the art would have been motivated to combine these references because doing so would allow for using ML models to identify data that may reveal abnormalities, as recognized by Bai. Thus, the claimed invention would have been obvious to one having ordinary skill in the art before the effective filing date.
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Vaghefi Rezaei et al. (US 2025/0308701 A1, with foreign priority to AU2022/901625, filed June 15, 2022, US PGPub used herein for mapping purposes) in view of Kanagasingam et al. (US 9,898,659 B2), as applied to claims 1, 3-4, 7, 10-11, 13, 16 and 18 above, and further in view of Emilie Bertaux Hegemann (US 2020/0174453 A1).
Regarding claim 12, Vaghefi Rezaei in view of Kanagasingam teaches the system of claim 11, wherein the training dataset includes anonymized patient data and corresponding images of the retina associated with a plurality of patients (Vaghefi Rezaei, Para. [0059], a fundus camera typically comprises an image capturing device, which in use is held close to the exterior of the eye and which illuminates and photographs the retina to provide a 2D image of part of the interior of the eye).
Although Vaghefi Rezaei in view of Kanagasingam teaches training data includes an indication of the patient having CVD (i.e., first condition) (Vaghefi Rezaei, Para. [0084]), the references do not explicitly teach the training dataset includes “an indication of whether one or more of the plurality of patients developed deep vein thrombosis”. However, in an analogous field of endeavor, Bertaux Hegemann teaches diagnosis options including i) chronic venous disorders or CVD, (ii) medical complex extremities or MCE and/or (iii) other patient indication (Bertaux Hegemann, Para. [0088]). “Other patient indication” includes indications about consumer/patient health that would benefit from therapeutic compression treatments (e.g. heavy legs, Deep Vein Thrombose (DVT), Venous Thromboembolism (VTE), etc.) (Bertaux Hegemann, Para. [0035]).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date to modify the system of Vaghefi Rezaei in view of Kanagasingam with the teachings of Bertaux Hegemann by including that the indication of the patient having the condition includes an indication of deep vein thrombose (DVT). One having ordinary skill in the art would have been motivated to combine these references because doing so would allow for preventing and/or treating chronic venous disorders, as recognized by Bertaux Hegemann. Thus, the claimed invention would have been obvious to one having ordinary skill in the art before the effective filing date.
Claims 15 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Vaghefi Rezaei et al. (US 2025/0308701 A1, with foreign priority to AU2022/901625, filed June 15, 2022, US PGPub used herein for mapping purposes) in view of Kanagasingam et al. (US 9,898,659 B2), as applied to claims 1, 3-4, 7, 10-11, 13, 16 and 18 above, and further in view of Morteza Naghavi (US 2023/0352181 A1).
Regarding claim 15, Vaghefi Rezaei in view of Kanagasingam teaches the system of claim 10, as described above.
Although Vaghefi Rezaei in view of Kanagasingam teaches a recommendation to a patient based on a risk level (Vaghefi Rezaei, Para. [0115]), the references do not explicitly teach “wherein the first condition is deep vein thrombosis (DVT) or pulmonary embolism (PE) and the recommendation includes at least one of: imaging tests to confirm DVT, D-dimer test, or prescription of thrombolytic medication”. However, in an analogous field of endeavor, Naghavi teaches assessing the clinical probability of PE (pulmonary embolism) for a patient. If the probability of PE is not high (that is, low or intermediate, for example), then a D-dimer test is performed (Naghavi, Para. [0098]).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Vaghefi Rezaei in view of Kanagasingam with the teachings of Naghavi by including that the condition is pulmonary embolism and the recommendation includes a D-dimer test. One having ordinary skill in the art would have been motivated to combine these references because doing so would allow for efficient risk assessment of patients, as recognized by Naghavi. Thus, the claimed invention would have been obvious to one having ordinary skill in the art before the effective filing date.
Regarding claim 17, Vaghefi Rezaei in view of Kanagasingam teaches the non-transitory computer-readable storage medium of claim 16, wherein the ML model is trained based on a training dataset comprising anonymized patient data and corresponding images of the retina associated with a plurality of patients (Vaghefi Rezaei, Para. [0059], a fundus camera typically comprises an image capturing device, which in use is held close to the exterior of the eye and which illuminates and photographs the retina to provide a 2D image of part of the interior of the eye).
Although Vaghefi Rezaei in view of Kanagasingam teaches an indication if an individual encounters a CVD event (Vaghefi Rezaei, Para. [0084]), the references do not explicitly teach the training dataset includes an “indication of whether the respective patient developed a blood clot-related condition”. However, in an analogous field of endeavor, Naghavi teaches PE can show chest pain symptom and can be caused by blood clots in pulmonary arteries. A blood clot puts pressure on the RV and causes it to become larger (Naghavi, Para. [0097]). Naghavi further teaches assessing the clinical probability of PE for a patient. The patient may have chest pain symptoms. At step 1610 it is determined if there is a high probability of PE (Naghavi, Para. [0098]).
The proposed combination as well as the motivation for combining the Vaghefi Rezaei, Kanagasingam, and Naghavi references presented in the rejection of Claim 15, apply to Claim 17 and are incorporated herein by reference. Thus, the computer readable medium recited in Claim 17 is met by Vaghefi Rezaei in view of Kanagasingam further in view of Naghavi.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Emma Rose Goebel whose telephone number is (703)756-5582. The examiner can normally be reached Monday - Friday 7:30-5.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Amandeep Saini can be reached at (571) 272-3382. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Emma Rose Goebel/Examiner, Art Unit 2662
/AMANDEEP SAINI/Supervisory Patent Examiner, Art Unit 2662
Prosecution Insights